Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration
An AI research paper on Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration.
Engineering 5.0 · Research 7.0 · Business 4.0
aipentium - AI Papers with Code, Datasets and Engineering Notes
aipentium: browse curated AI and robotics papers about humanoid robots, embodied AI, robot manipulation, VLA models, Diffusion Policy, Sim2Real and robot foundation models.
Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
An AI research paper on Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction.
Engineering 5.0 · Research 7.0 · Business 4.0
Cloud-Boosted Low-Compute Multi-Channel Speech Enhancement
An AI research paper on Cloud-Boosted Low-Compute Multi-Channel Speech Enhancement.
Engineering 5.0 · Research 7.0 · Business 4.0
CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing
An AI research paper on CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing.
Engineering 5.0 · Research 7.0 · Business 4.0
A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy
An AI research paper on A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy.
Engineering 5.0 · Research 7.0 · Business 4.0
TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
An AI research paper on TEPA: Revoking Stale Memories for Conflict-Robust Language Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
An AI research paper on Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits.
Engineering 5.0 · Research 7.0 · Business 4.0
Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control
An AI research paper on Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control.
Engineering 5.0 · Research 7.0 · Business 4.0
Conformal Coverage Guarantees for Any Video Temporal Grounder
An AI research paper on Conformal Coverage Guarantees for Any Video Temporal Grounder.
Engineering 5.0 · Research 7.0 · Business 4.0
SABRE: Scalable and Automated Benchmarking of VLMs under Stress
An AI research paper on SABRE: Scalable and Automated Benchmarking of VLMs under Stress.
Engineering 5.0 · Research 7.0 · Business 4.0
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
An AI research paper on Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers.
Engineering 5.0 · Research 7.0 · Business 4.0
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
An AI research paper on Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing.
Engineering 5.0 · Research 7.0 · Business 4.0
PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
An AI research paper on PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis
An AI research paper on An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis.
Engineering 5.0 · Research 7.0 · Business 4.0
Blast Radius
An AI research paper on Blast Radius.
Engineering 5.0 · Research 7.0 · Business 4.0
RIS-Aided mmWave Localization Under Cross-Link Interference via Beam-Domain ML Fingerprinting
An AI research paper on RIS-Aided mmWave Localization Under Cross-Link Interference via Beam-Domain ML Fingerprinting.
Engineering 5.0 · Research 7.0 · Business 4.0
Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools
An AI research paper on Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools.
Engineering 5.0 · Research 7.0 · Business 4.0
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
An AI research paper on SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent.
Engineering 5.0 · Research 7.0 · Business 4.0
Strategy-first synthesis planning for complex natural products
An AI research paper on Strategy-first synthesis planning for complex natural products.
Engineering 5.0 · Research 7.0 · Business 4.0
Interaction Creates Dynamical AI Behavior Absent in Isolation
An AI research paper on Interaction Creates Dynamical AI Behavior Absent in Isolation.
Engineering 5.0 · Research 7.0 · Business 4.0